In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!
Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the iPython Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to \n", "File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.
In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.
Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.
The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this IPython notebook.
In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).

In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!
We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.
In the code cell below, we import a dataset of dog images. We populate a few variables through the use of the load_files function from the scikit-learn library:
train_files, valid_files, test_files - numpy arrays containing file paths to imagestrain_targets, valid_targets, test_targets - numpy arrays containing onehot-encoded classification labels dog_names - list of string-valued dog breed names for translating labelsfrom sklearn.datasets import load_files
from keras.utils import np_utils
import numpy as np
from glob import glob
# define function to load train, test, and validation datasets
def load_dataset(path):
data = load_files(path)
dog_files = np.array(data['filenames'])
dog_targets = np_utils.to_categorical(np.array(data['target']), 133)
return dog_files, dog_targets
# load train, test, and validation datasets
train_files, train_targets = load_dataset('dogImages/train')
valid_files, valid_targets = load_dataset('dogImages/valid')
test_files, test_targets = load_dataset('dogImages/test')
# load list of dog names
dog_names = [item[20:-1] for item in sorted(glob("dogImages/train/*/"))]
# print statistics about the dataset
print('There are %d total dog categories.' % len(dog_names))
print('There are %s total dog images.\n' % len(np.hstack([train_files, valid_files, test_files])))
print('There are %d training dog images.' % len(train_files))
print('There are %d validation dog images.' % len(valid_files))
print('There are %d test dog images.'% len(test_files))
In the code cell below, we import a dataset of human images, where the file paths are stored in the numpy array human_files.
import random
random.seed(8675309)
# load filenames in shuffled human dataset
human_files = np.array(glob("lfw/*/*"))
random.shuffle(human_files)
# print statistics about the dataset
print('There are %d total human images.' % len(human_files))
We use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images. OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades directory.
In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.
import cv2
import matplotlib.pyplot as plt
%matplotlib inline
# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')
# load color (BGR) image
img = cv2.imread(human_files[3])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# find faces in image
faces = face_cascade.detectMultiScale(gray)
# print number of faces detected in the image
print('Number of faces detected:', len(faces))
# get bounding box for each detected face
for (x,y,w,h) in faces:
# add bounding box to color image
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale function executes the classifier stored in face_cascade and takes the grayscale image as a parameter.
In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.
We can use this procedure to write a function that returns True if a human face is detected in an image and False otherwise. This function, aptly named face_detector, takes a string-valued file path to an image as input and appears in the code block below.
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
img = cv2.imread(img_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray)
return [len(faces) > 0, faces]
Question 1: Use the code cell below to test the performance of the face_detector function.
human_files have a detected human face? dog_files have a detected human face? Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short and dog_files_short.
Answer:
human_files_short = human_files[:100]
dog_files_short = train_files[:100]
# Do NOT modify the code above this line.
## TODO: Test the performance of the face_detector algorithm
## on the images in human_files_short and dog_files_short.
# display the image, along with bounding box
# in human files
pos_idx = {}
total_cnt = 0
for idx, img_path in enumerate(human_files_short):
pos, faces = face_detector(img_path)
if pos == True:
pos_idx[idx] = faces
else:
img = cv2.imread(img_path)
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
plt.title('undetected')
plt.show()
total_cnt += 1
print('{}% is detected in humans.'.format(len(pos_idx) / total_cnt * 100))
fig = plt.figure(figsize=(32, 32))
img_i = 1
cols = 10
rows = 10
# show detected images
for idx in pos_idx.keys():
img = cv2.imread(human_files_short[idx])
fig.add_subplot(rows, cols, img_i)
img_i += 1
# get bounding box for each detected face
faces = pos_idx[idx]
for (x,y,w,h) in faces:
# add bounding box to color image
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
plt.show()
# in dog files
fig = plt.figure(figsize=(32, 32))
img_i = 1
cols = 10
rows = 10
pos_idx.clear()
total_cnt = 0
for idx, img_path in enumerate(dog_files_short):
pos, faces = face_detector(img_path)
if pos == True:
pos_idx[idx] = faces
total_cnt += 1
print('{}% is detected in dogs.'.format(len(pos_idx) / total_cnt * 100))
# show detected images
for idx in pos_idx.keys():
img = cv2.imread(dog_files_short[idx])
fig.add_subplot(rows, cols, img_i)
img_i += 1
# get bounding box for each detected face
faces = pos_idx[idx]
for (x,y,w,h) in faces:
# add bounding box to color image
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
plt.show()
Question 2: This algorithmic choice necessitates that we communicate to the user that we accept human images only when they provide a clear view of a face (otherwise, we risk having unneccessarily frustrated users!). In your opinion, is this a reasonable expectation to pose on the user? If not, can you think of a way to detect humans in images that does not necessitate an image with a clearly presented face?
Answer: It depends on the necessity of an application. It will be worth when the application is interactive like a locking system using human face. But if the application is a monitoring or detecting system which cannot be interactive with human, this will be a huge weakness. To detect humans, I can think several ways such as detecting face, hair, clothes, shape, and so on. So, building up a neural network would return comprehensive result for detecting humans.
We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :). Please use the code cell below to design and test your own face detection algorithm. If you decide to pursue this optional task, report performance on each of the datasets.
## (Optional) TODO: Report the performance of another
## face detection algorithm on the LFW dataset
### Feel free to use as many code cells as needed.
In this section, we use a pre-trained ResNet-50 model to detect dogs in images. Our first line of code downloads the ResNet-50 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories. Given an image, this pre-trained ResNet-50 model returns a prediction (derived from the available categories in ImageNet) for the object that is contained in the image.
from keras.applications.resnet50 import ResNet50
# define ResNet50 model
ResNet50_model = ResNet50(weights='imagenet')
When using TensorFlow as backend, Keras CNNs require a 4D array (which we'll also refer to as a 4D tensor) as input, with shape
$$ (\text{nb_samples}, \text{rows}, \text{columns}, \text{channels}), $$
where nb_samples corresponds to the total number of images (or samples), and rows, columns, and channels correspond to the number of rows, columns, and channels for each image, respectively.
The path_to_tensor function below takes a string-valued file path to a color image as input and returns a 4D tensor suitable for supplying to a Keras CNN. The function first loads the image and resizes it to a square image that is $224 \times 224$ pixels. Next, the image is converted to an array, which is then resized to a 4D tensor. In this case, since we are working with color images, each image has three channels. Likewise, since we are processing a single image (or sample), the returned tensor will always have shape
$$ (1, 224, 224, 3). $$
The paths_to_tensor function takes a numpy array of string-valued image paths as input and returns a 4D tensor with shape
$$ (\text{nb_samples}, 224, 224, 3). $$
Here, nb_samples is the number of samples, or number of images, in the supplied array of image paths. It is best to think of nb_samples as the number of 3D tensors (where each 3D tensor corresponds to a different image) in your dataset!
from keras.preprocessing import image
from tqdm import tqdm
def path_to_tensor(img_path):
# loads RGB image as PIL.Image.Image type
img = image.load_img(img_path, target_size=(224, 224))
# convert PIL.Image.Image type to 3D tensor with shape (224, 224, 3)
x = image.img_to_array(img)
# convert 3D tensor to 4D tensor with shape (1, 224, 224, 3) and return 4D tensor
return np.expand_dims(x, axis=0)
def paths_to_tensor(img_paths):
list_of_tensors = [path_to_tensor(img_path) for img_path in tqdm(img_paths)]
return np.vstack(list_of_tensors)
Getting the 4D tensor ready for ResNet-50, and for any other pre-trained model in Keras, requires some additional processing. First, the RGB image is converted to BGR by reordering the channels. All pre-trained models have the additional normalization step that the mean pixel (expressed in RGB as $[103.939, 116.779, 123.68]$ and calculated from all pixels in all images in ImageNet) must be subtracted from every pixel in each image. This is implemented in the imported function preprocess_input. If you're curious, you can check the code for preprocess_input here.
Now that we have a way to format our image for supplying to ResNet-50, we are now ready to use the model to extract the predictions. This is accomplished with the predict method, which returns an array whose $i$-th entry is the model's predicted probability that the image belongs to the $i$-th ImageNet category. This is implemented in the ResNet50_predict_labels function below.
By taking the argmax of the predicted probability vector, we obtain an integer corresponding to the model's predicted object class, which we can identify with an object category through the use of this dictionary.
from keras.applications.resnet50 import preprocess_input, decode_predictions
def ResNet50_predict_labels(img_path):
# returns prediction vector for image located at img_path
img = preprocess_input(path_to_tensor(img_path))
return np.argmax(ResNet50_model.predict(img))
While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua' to 'Mexican hairless'. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained ResNet-50 model, we need only check if the ResNet50_predict_labels function above returns a value between 151 and 268 (inclusive).
We use these ideas to complete the dog_detector function below, which returns True if a dog is detected in an image (and False if not).
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
prediction = ResNet50_predict_labels(img_path)
return [((prediction <= 268) & (prediction >= 151)), prediction]
Question 3: Use the code cell below to test the performance of your dog_detector function.
human_files_short have a detected dog? dog_files_short have a detected dog?Answer:
### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.
# in human files
pos_idx = {}
total_cnt = 0
for idx, img_path in enumerate(human_files_short):
pos, prediction = dog_detector(img_path)
if pos == True:
pos_idx[idx] = prediction
total_cnt += 1
print('{}% is detected in humans.'.format(len(pos_idx) / total_cnt * 100))
# show detected images
for idx, prediction in pos_idx.items():
img = cv2.imread(human_files_short[idx])
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
plt.show()
print('prediction =', prediction)
# in dog files
pos_idx.clear()
total_cnt = 0
for idx, img_path in enumerate(dog_files_short):
pos, prediction = dog_detector(img_path)
if pos == True:
pos_idx[idx] = img_path
total_cnt += 1
print('{}% is detected in dogs.'.format(len(pos_idx) / total_cnt * 100))
Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 1%. In Step 5 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.
Be careful with adding too many trainable layers! More parameters means longer training, which means you are more likely to need a GPU to accelerate the training process. Thankfully, Keras provides a handy estimate of the time that each epoch is likely to take; you can extrapolate this estimate to figure out how long it will take for your algorithm to train.
We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have great difficulty in distinguishing between a Brittany and a Welsh Springer Spaniel.
| Brittany | Welsh Springer Spaniel |
|---|---|
![]() |
![]() |
It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).
| Curly-Coated Retriever | American Water Spaniel |
|---|---|
![]() |
![]() |
Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.
| Yellow Labrador | Chocolate Labrador | Black Labrador |
|---|---|---|
![]() |
![]() |
![]() |
We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.
Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!
We rescale the images by dividing every pixel in every image by 255.
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
# pre-process the data for Keras
train_tensors = paths_to_tensor(train_files).astype('float32')/255
valid_tensors = paths_to_tensor(valid_files).astype('float32')/255
test_tensors = paths_to_tensor(test_files).astype('float32')/255
Create a CNN to classify dog breed. At the end of your code cell block, summarize the layers of your model by executing the line:
model.summary()
We have imported some Python modules to get you started, but feel free to import as many modules as you need. If you end up getting stuck, here's a hint that specifies a model that trains relatively fast on CPU and attains >1% test accuracy in 5 epochs:

Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. If you chose to use the hinted architecture above, describe why you think that CNN architecture should work well for the image classification task.
Answer: I tried to extract features 4 times as 32, 64, 128, and 256 in order using 'Conv2D'. And between layers, I tried to maximize the difference using 'MaxPooling2D' respectively. For the memory reason, I used 'GlobalAveragePolling2D' to make a fully connected layer. Finally, to classify the breed of dog, I used 133 'Dense' layer.
from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D
from keras.layers import Dropout, Flatten, Dense
from keras.models import Sequential
model = Sequential()
### TODO: Define your architecture.
model.add(Conv2D(filters=32, kernel_size=5, padding='same', activation='relu', input_shape=(224, 224, 3)))
model.add(MaxPooling2D(pool_size=2))
model.add(Conv2D(filters=64, kernel_size=5, padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Conv2D(filters=128, kernel_size=5, padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Conv2D(filters=256, kernel_size=5, padding='same', activation='relu'))
model.add(GlobalAveragePooling2D())
model.add(Dropout(0.2))
model.add(Dense(133, activation='softmax'))
model.summary()
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
Train your model in the code cell below. Use model checkpointing to save the model that attains the best validation loss.
You are welcome to augment the training data, but this is not a requirement.
from keras.callbacks import ModelCheckpoint
ImageFile.LOAD_TRUNCATED_IMAGES = True
### TODO: specify the number of epochs that you would like to use to train the model.
epochs = 50
### Do NOT modify the code below this line.
checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.from_scratch.hdf5',
verbose=1, save_best_only=True)
history = model.fit(train_tensors, train_targets,
validation_data=(valid_tensors, valid_targets),
epochs=epochs, batch_size=20, callbacks=[checkpointer], verbose=1)
import matplotlib.pyplot as plt
%matplotlib inline
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'valid'], loc='upper left')
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'valid'], loc='upper left')
plt.show()
from keras import backend as K
# util function to convert a tensor into a valid image
def deprocess_image(x):
# normalize tensor: center on 0., ensure std is 0.1
x -= x.mean()
x /= (x.std() + 1e-5)
x *= 0.1
# clip to [0, 1]
x += 0.5
x = np.clip(x, 0, 1)
# convert to RGB array
x *= 255
if K.image_dim_ordering() == 'th':
x = x.transpose((1, 2, 0))
x = np.clip(x, 0, 255).astype('uint8')
return x
def normalize(x):
# utility function to normalize a tensor by its L2 norm
return x / (K.sqrt(K.mean(K.square(x))) + K.epsilon())
def get_filters_img(filters, img_width, img_height):
margin = 5
n = int(len(filters)**0.5)
width = n * img_width + (n - 1) * margin
height = n * img_height + (n - 1) * margin
stitched_filters = np.zeros((width, height, 3))
# fill the picture with our saved filters
for i in range(n):
for j in range(n):
index = i * n + j
if index < len(filters):
img = filters[i * n + j]
stitched_filters[(img_width + margin) * i: (img_width + margin) * i + img_width,
(img_height + margin) * j: (img_height + margin) * j + img_height, :] = img
return stitched_filters
from matplotlib.pyplot import imshow
%matplotlib inline
img_width = 224
img_height = 224
input_img = image.load_img(train_files[0], target_size=(img_width, img_height))
input_img = np.asarray(input_img)
imshow(input_img)
import math
import time
def show_layer_output(layer_name, filters_num, img_width=224, img_height=224):
input_placeholder = model.input
kept_filters = []
for filter_index in range(filters_num):
# we build a loss function that maximizes the activation
# of the nth filter of the layer considered
layer_output = layer_dict[layer_name].output
if K.image_data_format() == 'channels_first':
loss = K.mean(layer_output[:, filter_index, :, :])
else:
loss = K.mean(layer_output[:, :, :, filter_index])
# we compute the gradient of the input picture with this loss
grads = K.gradients(loss, input_placeholder)[0]
# normalization trick: we normalize the gradient
grads = normalize(grads)
# this function returns the loss and grads given the input picture
iterate = K.function([input_placeholder], [loss, grads])
# step size for gradient ascent
step = 1.
'''
# we start from a sample image from the training set
if K.image_data_format() == 'channels_first':
input_img_data = np.asarray([np.transpose(input_img, (2, 0, 1))], dtype='float32')
else:
input_img_data = np.asarray([input_img], dtype='float32')
'''
# we start from a gray image with some random noise
if K.image_data_format() == 'channels_first':
input_img_data = np.random.random((1, 3, img_width, img_height))
else:
input_img_data = np.random.random((1, img_width, img_height, 3))
input_img_data = (input_img_data - 0.5) * 20 + 128
# we run gradient ascent for 20 steps
for i in range(20):
loss_value, grads_value = iterate([input_img_data])
input_img_data += grads_value * step
if loss_value <= 0.:
# some filters get stuck to 0, we can skip them
break
# decode the resulting input image
if loss_value > 0:
img = deprocess_image(input_img_data[0])
kept_filters.append((img, loss_value))
end_time = time.time()
# we will stich the best 64 filters on a 8 x 8 grid.
n = 8
kept_size = kept_max = n * n
# the filters that have the highest loss are assumed to be better-looking.
kept_filters.sort(key=lambda x: x[1], reverse=True)
if len(kept_filters) > kept_max:
kept_filters = kept_filters[:kept_max]
else:
kept_size = len(kept_filters)
# build a black picture with enough space for
# our 8 x 8 filters of size 224 x 224, with a 5px margin in between
margin = 5
width = n * img_width + (n - 1) * margin
row_cnt = math.ceil(kept_size / n)
height = row_cnt * img_height + (row_cnt - 1) * margin
stitched_filters = np.zeros((height, width, 3))
# fill the picture with our saved filters
kept_idx = 0
for i in range(row_cnt):
for j in range(n):
if kept_idx >= kept_size:
break
img, loss = kept_filters[kept_idx]
kept_idx += 1
stitched_filters[(img_height + margin) * i: (img_height + margin) * i + img_height,
(img_width + margin) * j: (img_width + margin) * j + img_width, :] = img
return stitched_filters
# filters_num = iter([16, 32, 64, 128, 256])
filters_num = iter([32, 64, 128, 256, 512])
layer_dict = dict([(layer.name, layer) for layer in model.layers])
for key in layer_dict:
if key.startswith('conv2d_'):
fig = plt.figure(figsize=(32, 32))
plt.title(key)
imshow(show_layer_output(key, next(filters_num)), interpolation='none')